Generate game art from Claude Code
Claude Code gets the richest integration of any agent — a packaged skill with its own slash commands, not just an instruction file.
Point Claude Code at the MCP server.
40 tools over one endpoint — list, read, export, curate frames, generate. Same key, same guardrails as the REST API, and paid tools preview their cost before they run.
claude mcp add --transport http spriteship \ https://spriteship.com/mcp \ --header "Authorization: Bearer $SPRITESHIP_API_KEY" # 40 tools, immediately. Ask: "list my SpriteShip characters"
Verified against Claude Code’s MCP docs — note it is --header, not -e. If the header is rejected Claude Code reports a hard failure rather than falling back to OAuth, so a stale key looks like a broken server.
# 1. Point your agent's shell at your key export SPRITESHIP_API_KEY="ss_live_..." # 2. Confirm it works curl -sS -H "Authorization: Bearer $SPRITESHIP_API_KEY" \ https://spriteship.com/api/v1/me # 3. Teach the agent the API — the skill ships an AGENTS.md cat <spriteship-skill>/AGENTS.md >> AGENTS.md
Add the skill too.
MCP gives Claude Code the tools. The skill gives it the recipes — how to sync into a project tree, how to re-sync only what changed, and the protocol it must follow before spending a credit. They compose.
# Copy the skill into your game project
mkdir -p .claude/skills
cp -R <spriteship-repo>/agent-skill/skills/spriteship \
.claude/skills/spriteship
# Claude Code picks it up automatically. Then just ask:
# "sync my SpriteShip knight into assets/"Claude Code reads CLAUDE.md natively and also honours the cross-tool AGENTS.md. The skill folder adds the full endpoint reference, sync recipes and the credit-spending protocol. <spriteship-skill> is the SpriteShip agent skill — getting the skill →
Built for how Claude Code works.
Four slash commands
/spriteship:setup verifies your key and scaffolds the asset folder. :sync pulls an entity or re-syncs everything in the lock file. :list shows projects and ids. :credits shows the balance and what this key spent. All read-only and free.
Spending is a protocol, not a call
There is deliberately no slash command for paid generation. Spending always starts from conversation and runs the skill’s protocol: dry-run cost preview, your explicit confirmation, idempotency key, poll, then reconcile against the ledger.
It reads the exports it downloads
Each export zip ships its own SKILL.md and JSON Schema, so after a sync Claude Code already knows how to wire that bundle into Phaser, Godot, Unity or GameMaker.
One ask, start to finish.
"pull my forest tileset and build a starter level from it"
- 01Lists your projects and finds the tileset by name
- 02Downloads the Tiled bundle — tileset image, .tsj, and per-tile collision
- 03Writes it into assets/spriteship/forest/ and records spriteship.lock.json
- 04Generates a starter .tmj that references the tileset with real colliders
The full loop, once.
Every agent runs the same shape — resolve, preview the cost, confirm, generate, poll, write the files, wire the code.
you › the knight needs a dodge-roll animation, then wire it into the player state machine
agent › GET /api/v1/characters?name=knight
→ chr_8fq2… · contentVersion 4a1c… · 6 animations
agent › POST /api/v1/characters/chr_8fq2…/generate-pose { dryRun: true }
→ 400 credits · balance 1,500 → 1,100
you › go ahead
agent › POST /api/v1/characters/chr_8fq2…/generate-pose
Idempotency-Key: 7c1f-…
→ job_2b9e… queued
agent › GET /api/v1/jobs/job_2b9e… → running
agent › GET /api/v1/jobs/job_2b9e… → done · 400 credits charged
agent › GET /api/v1/characters/chr_8fq2…/export?engine=phaser&format=json
→ wrote assets/spriteship/knight/spritesheet.png
wrote assets/spriteship/knight/atlas.json
wrote spriteship.lock.json (contentVersion 91be…)
agent › edited src/player/PlayerStateMachine.ts
+ case 'dodge': this.play('dodge_roll'); break;
done — dodge_roll is registered and playable. 400 credits spent.Handing an agent a budget, safely.
An agent that can spend money needs more than an API key. Every one of these is enforced server-side — not a convention the agent is trusted to follow.
Scoped keys
Four scopes, granted separately: assets:read, account:read, assets:write, credits:spend. A read-only key physically cannot spend money.
Per-key spend caps
Every key carries a daily credit ceiling — 5,000 by default, 50,000 maximum. Accounting is gross, so refunds restore your balance but never hand the key back headroom.
Over MCP, paid tools preview by default
Every paid MCP tool defaults to a dry run: it returns the exact credit cost and your resulting balance, and executes nothing. The agent has to deliberately re-call with dryRun:false to spend. Accidental spend is not a thing it can stumble into.
Idempotency keys
Paid writes require an Idempotency-Key header. A retried request replays the original job pointer instead of starting — and paying for — a second generation.
Busy-entity guard
A write against an entity that already has a job running answers ENTITY_BUSY rather than racing it, so two agents (or one confused agent) cannot corrupt the same character.
Re-sync signals
Every read carries contentVersion or updatedAt. The agent diffs those against its lock file and re-downloads only what actually changed after you edited something in the dashboard.
Presigned binaries
Every sheet, atlas, zip and preview URL is presigned and expiring. Nothing in an API response is a permanent public link.
Kill switch
Revoking a key cancels its in-flight jobs and refunds their unfinished charges. Leaked keys found by GitHub secret scanning are revoked automatically and you get an email.
Output an agent can actually use.
A folder of PNGs makes an agent guess. Every SpriteShip export explains itself, so the agent wires it up instead of improvising.
Self-describing bundles
Every export zip carries a manifest (tizo-export.json), a JSON Schema of its own shape, a README, a runnable preview and a SKILL.md — so an agent can consume the output without you explaining the format.
Native engine files
Phaser atlases, Godot 4 .tres resources, Unity sliced sprites with stable GUIDs, GameMaker sprite strips and Tiled tilesets. Not a folder of PNGs the agent has to guess at.
Collision, not bounding boxes
Authored collision bodies and ground footprints ride through the API and into every export, so the agent builds the real collider instead of defaulting to the sprite rectangle.
Mount points
Per-frame anchor points for weapons, hands and heads travel with the animation, so the agent can parent a projectile spawn to the right pixel on the right frame.
Claude Code, specifically.
Do I need the plugin marketplace install?
Not today. The skill repo is still inside the SpriteShip monorepo, so the copy-the-folder install above is the one that works. The /plugin marketplace one-liners activate when the skill is extracted to its own public repo.
Can Claude Code spend my credits without asking?
Only if you grant the key the credits:spend scope, and even then the skill requires a dry-run preview plus your confirmation first. A key without that scope is physically incapable of spending. Every key also has a daily cap.
Related
Cursor reads project rules from .cursor/rules — drop the SpriteShip rule there and Composer can fetch art the same way it fetches a package.
Windsurf reads workspace rules from .windsurf/rules — and the cross-tool AGENTS.md at your repo root — so the setup is one file and one env var.
Cline reads .clinerules, runs in your editor with your terminal, and asks before acting — which lines up exactly with how paid generation is designed to work.
Point Claude Code
at your art.
1,500 free credits, no card. Reading and re-syncing never cost anything.
Start free — 1,500 credits